Benchmark result
gemma4:e2b on NVIDIA GeForce RTX 4060 Laptop GPU — 90.7 tok/s
Measured with Ollama 0.32.15 on August 23, 2026.
Support llm-bench.io
llm-bench.io is free. If it helped you, I'd appreciate your support to cover the infrastructure costs.
What the model built
Open full screen →The coding scenario asks for a playable game in a single HTML file. This is exactly what the model returned, unedited; the frame only adds a line that tells this page how tall it is.
How this run compares
gemma4:e2b on other hardware
- 158.5tok/s73.4NVIDIA RTX 3500 Ada Generation Laptop GPU · Q4_K_M
- 157.9tok/s71.6NVIDIA RTX 3500 Ada Generation Laptop GPU · Q4_K_M
- 157.8tok/s69.2NVIDIA RTX 3500 Ada Generation Laptop GPU · Q4_K_M
- 157.6tok/s68.2NVIDIA RTX 3500 Ada Generation Laptop GPU · Q4_K_M
- 156.6tok/s64.4NVIDIA RTX 3500 Ada Generation Laptop GPU · Q4_K_M
Reproduce this run
toolOllama 0.32.15
modelgemma4:e2b (Q4_K_M)
context8,192
clientv0.4.42+97
Set those in Ollama, then:
llm-benchmark benchmark --model "gemma4:e2b" --tool "Ollama"The client prompts for context length and thinking mode, and for the KV cache dtype on Unsloth Studio. Sampling is left at the model default — the values above are what the tool reported using, not overrides the client sent.